© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4279
    Prev
    Next
    INDEX
    Explanations

    mentions of international or foreign policy

    oai_token-act-pair · gemini-2.0-flash

    foreign

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.56
     terletak
    -0.53
    Мир
    -0.51
     provas
    -0.49
    gyar
    -0.46
     stopper
    -0.46
    ്യ
    -0.45
     der
    -0.45
     revient
    -0.44
    ifrance
    -0.43
    POSITIVE LOGITS
    ChildScrollView
    0.79
     HasFactory
    0.78
     виправивши
    0.77
    setVerticalGroup
    0.76
     للاسماء
    0.75
     resourceCulture
    0.73
    Personensuche
    0.69
    SharedCtor
    0.67
    клопе
    0.65
     تضيفلها
    0.64
    Activations Density 0.815%

    No Known Activations